LLM API Cost Calculator

Prices verified · 2026-08-03 · 12 model tiers

1

Choose a development workload

2

Configure budget assumptions

View model pricing
Advanced assumptions (optional)

One active session with recurring project context

3

Like-for-like model comparison

400K tokens/h · 80:20 · 25% cache

View methodology
ModelInput / 1MOutput / 1MCacheHourlyDailyMonthlySource
Claude Sonnet 4.6Anthropic Current$3$15$0.3¥14¥70¥1,540Anthropic list prices ↗
DeepSeek V4 FlashDeepSeek $0.14$0.28$0.0028¥0.4¥2.02¥45DeepSeek API ↗
DeepSeek V4 ProDeepSeek $0.435$0.87$0.0036¥1.25¥6.27¥138DeepSeek API ↗
Gemini 3.1 Flash-LiteGoogle $0.25$1.5$0.025¥1.31¥6.55¥144Gemini API ↗
Qwen 3.7 PlusAlibaba Cloud ¥2.998¥11.991¥0.6¥1.73¥8.63¥190Alibaba Cloud Model Studio ↗
Claude Haiku 4.5Anthropic $1$5$0.1¥4.67¥23¥513Anthropic list prices ↗
GPT-5.6 LunaOpenAI $1$6$0.1¥5.24¥26¥577OpenAI API ↗
Gemini 3.5 FlashGoogle $1.5$9$0.15¥7.86¥39¥865Gemini API ↗
Gemini 3.1 ProGoogle $2$12$0.2¥10¥52¥1,153Gemini API ↗
GPT-5.6 TerraOpenAI $2.5$15$0.25¥13¥66¥1,441OpenAI API ↗
Claude Opus 4.7Anthropic $5$25$0.5¥23¥117¥2,566Anthropic list prices ↗
GPT-5.6 SolOpenAI $5$30$0.5¥26¥131¥2,883OpenAI API ↗
Calculation method
Hourly cost = uncached input × input rate + cached input × cache rate + output × output rate

All token rates are per million; concurrent agents scale both input and output volume.

Official pricing sources

Prices last verified 2026-08-03. Open each provider source from the comparison table.

Billing boundaries and limits

Tools, code sandboxes, web search, and file retrieval may be billed separately.

Long-context tiers: Some models apply higher request-level rates beyond context thresholds.

Cache writes and storage: Explicit cache creation, storage, taxes, and channel charges are excluded.

Platform markups: Bedrock, Vertex AI, Azure, and resellers may differ from direct provider rates.

Scenario bands are editable planning assumptions, not industry averages or model-speed guarantees.

This planning tool is not a quote. Recheck provider pages, region, context tier, batch mode, and contract discounts before production.